@article{dontignorethetaildecouplingtopkprobabili,
  title = {Don't Ignore the Tail: Decoupling top-K Probabilities for Efficient Language Model Distillation},
  author = {Sayantan Dasgupta and Trevor Cohn and Timothy Baldwin},
  year = {2026},
  eprint = {2602.20816},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2602.20816},
}